Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/danielrosehill/claude-data-analyst-plugin/data-reportingnpx skills add danielrosehill/Claude-Data-Analyst-plugin --skill data-reportinggit clone --depth 1 https://github.com/danielrosehill/Claude-Data-Analyst-pluginWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00057 | $0.01809 |
| Opus 5 | $0.00028 | $0.00905 |
| Sonnet 5 | $0.00011 | $0.00362 |
| Haiku 4.5 | $0.00006 | $0.00181 |
Grade A, and why
data-reporting scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 170 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Data Reporting
Generate a parametric dataset report as a Typst-compiled PDF. "Parametric" here means the report structure is fixed and reusable — you fill in the parameters (dataset path, title, sections to include, cut-offs) and the document regenerates from scratch.
Use this skill when the user wants:
- A stakeholder-ready PDF describing a dataset.
- A reproducible document that can be regenerated on data refresh.
- A consolidation of outputs from other skills (
data-dictionary-creator,trend-analysis,correlation-analysis,standard-deviation,sample-size,forensic-sweep, etc.) into one artefact.
For quick markdown summaries, use the reporting step inside the relevant analysis skill instead — this skill is for when PDF is the deliverable.
Inputs
- Path to a dataset (CSV / Parquet / Excel / DuckDB table).
- Report parameters (all optional; sensible defaults applied):
title— report title. Default: dataset filename.subtitle— e.g. snapshot date.author— defaults to system user.sections— which sections to include. Default:overview,schema,size,distributions,quality,findings.max_columns_profiled— cap detailed profiling for very wide tables. Default: 50.include_charts— boolean. Default: true.theme—plain/dsr-business/personal. Default:plain.
Recommended tooling
duckdb— all stat computation.uv run --with pandas --with matplotlib python -c '...'— distribution plots rendered to PNG for Typst to embed. Matplotlib only (no seaborn) to keep dependencies minimal.typst— compile the document.- The
typst-document-generatorskills (public-doc,personal-doc,dsr-business-doc) — for themed output. Whentheme != plain, delegate final compilation to the matching skill.
Output layout
Create an output folder: outputs/data-reporting/<dataset-stem>-<YYYYMMDD>/:
outputs/data-reporting/sales-2026-04-23/
report.typ -- the Typst source
report.pdf -- compiled output
assets/
hist_price.png
hist_quantity.png
bar_category.png
missingness.png
data/
summary_stats.csv
schema.csv
params.json -- exact parameters used, for reproducibility
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 170 lines · 57 tokens per session scan A 2f2c516b1ac8
data-reporting is a skill published in the GitHub repository danielrosehill/Claude-Data-Analyst-plugin (11 stars, last pushed 4mo ago), licensed MIT. It adds 57 tokens to every session and 1,809 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
pdf-analysis
PDF 文档解析。自动区分文字型 PDF 与扫描型 PDF，覆盖：文本/表格提取、多页全量扫描、嵌入图表 caption、单位感知数值计算。.
sn-da-non-spreadsheet-analysis
Word / PDF / PPT 文档解析与数据分析引擎。覆盖三类文件格式的全量提取、表格数值化、图表理解与跨文档汇总分析。遇到以下任一情况就主动使用本 skill：①用户上传或指定了 .docx / .doc / .pdf / .pptx / .ppt 文件并要求分析、提取或统计其中内容；②用户出现触发词：Word分析 / PDF解析 / PPT提取 / 文档分析 / 报告解析 / 幻灯片分析 / 发票提取 / 合同分析 / 文档统计 / 错别字 / 语病 / 字号检查 / 简历分析 / 多文档对比；③任务涉及从文档中提取表格、数值、图表、格式（颜色/高亮/字号）、组织架构、时间线等结构化信息。仅不用于：Excel/CSV…
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
Use this skill whenever the user wants to do anything with PDF files. This includes reading or extracting text/tables from PDFs, combining or merging multiple PDFs into one, splitting PDFs apart, rotating pages, adding watermarks, creating new PDFs, filling PDF forms, encrypting/decrypting PDFs, extracting images, and…
sn-da-large-file-analysis
万行以上 Excel 数据集的高性能分析引擎。提供 openpyxl readonly 流式读取（iterrows 支持 10 万行以上）、Parquet 转换加速、内存优化、分块处理和大文件写入模式。遇到以下任一情况就主动使用本 skill：①数据行数 ≥ 10k（由 sn-da-excel-workflow 的行数评估步骤触发）；②用户出现触发词：大文件 / 大数据量 / 性能优化 / 内存不足 / OOM / 百万行 / 十万行 / 流式读取 / Parquet / 分块处理 / large file / big data / streaming read / chunked processing；③直接使用…
category-filtering-and-difficulty-analysis
对Excel数据进行自定义分类统计、交叉分析与可视化，并基于多维度指标（如文本长度、术语密度、正则匹配等）进行综合评分与分级，适用于多类别数据分布统计及文本内容难度/质量评估场景。.